git-dig-history

#! /bin/sh

### Copyright (C) 2017 by Jim Klimov

usage() {
    cat << EOF
You can call this script as
    $0 find_commits_contains [PATTERN]      commit context or content matches
    $0 find_commits_show [PATTERN]          colorful show of above commits body
    $0 find_commits_intro [PATTERN]         commits which add the pattern
    $0 find_commits_drop [PATTERN]          commits which remove the pattern
    $0 fix_history [PATTERN] [REPLACEMENT]

Note that PATTERN and REPLACEMENT are fixed strings (not regexes) in this context
For the SED usage there is also a PATTERN_SED that you can optionally export
EOF
}

[ -n "${PATTERN-}" ] || PATTERN="needle"
[ -n "${REPLACEMENT-}" ] || REPLACEMENT="@CUSTOM_NEEDLE@"
### This script runs from the basedir of a git repo (or a few)
### Logs and other work files are commonly stored in the parent dir by default
[ -n "${LOGDIR-}" ] || LOGDIR="`pwd`/.."
[ -n "${LOGTAG-}" ] || LOGTAG="$(basename `pwd`)"

if [ -z "${GGREP-}" ] ; then
	# TODO: check if GNU Grep extensions (-A<NUM>) are supported?
	(command -v ggrep 2>/dev/null >/dev/null) && GGREP=ggrep || GGREP=grep
fi

find_commits_contains() {
    ### This lists which "$COMMITID:$PATHNAME:$LINETEXT" contain the PATTERN in the LINETEXT
    ### Note that this lists all commits whose checked-out workspace would have the pattern
    [ -n "${WORKSPACE_MATCHES_FILE-}" ] || WORKSPACE_MATCHES_FILE="${LOGDIR}/gitdig_commits-workspace-contains__${LOGTAG}.txt"
    git grep "${PATTERN}" $(git rev-list --all --remotes) \
    | tee "${WORKSPACE_MATCHES_FILE}"
}

show_commits_color() {
    ### This finds which commits dealt with the pattern (whose diff
    ### adds or removes a line with it, or has it in context)
    ### Note that this starts with a colorful depiction of first-pass
    ### diffs, for esthetic viewing pleasure and is parsed including
    ### color markup by other tools below
    git rev-list --all --remotes | \
        while read CMT ; do ( \
            git show --color --pretty='format:%b' "$CMT" | \
            egrep "${PATTERN}" && echo "^^^ $CMT" \
        ) ; done
}

find_commits_show() {
    # alias
    show_commits_color "$@"
}

find_commits_intro() {
    ### This finds which commits INTRODUCE the pattern (whose diff adds a line with it)
    ### Note that this starts with a colorful depiction of first-pass diffs, for esthetic viewing pleasure
    [ -n "${COMMIT_INTRODUCES_FILE-}" ] || COMMIT_INTRODUCES_FILE="${LOGDIR}/gitdig_commits-intro__${LOGTAG}.txt"
    show_commits_color | tee "${COMMIT_INTRODUCES_FILE}".tmp

    ### ...and this picks out the lines for commits which actually add the PATTERN
    ### (because there are also not interesting context and removal lines as well,
    ### which should disappear after the rebase)
    echo "LIST OF COMMITS THAT INTRODUCE PATTERN (cached in ${COMMIT_INTRODUCES_FILE}.tmp) :"
    cat "${COMMIT_INTRODUCES_FILE}".tmp | \
    egrep '^([\^]|.*32m\+)' | \
    $GGREP -A1 '32m\+' | \
    grep '^\^' \
    | tee "${COMMIT_INTRODUCES_FILE}"
}

find_commits_drop() {
    ### This finds which commits REMOVE the pattern (whose diff drops a line with it)
    ### Note that this starts with a colorful depiction of first-pass diffs, for esthetic viewing pleasure
    [ -n "${COMMIT_DROPS_FILE-}" ] || COMMIT_DROPS_FILE="${LOGDIR}/gitdig_commits-drop__${LOGTAG}.txt"
    show_commits_color | tee "${COMMIT_DROPS_FILE}".tmp

    ### ...and this picks out the lines for commits which actually add the PATTERN
    ### (because there are also not interesting context and removal lines as well,
    ### which should disappear after the rebase)
    echo "LIST OF COMMITS THAT DROP THE PATTERN (cached in ${COMMIT_DROPS_FILE}.tmp) :"
    cat "${COMMIT_DROPS_FILE}".tmp | \
    egrep '^([\^]|.*31m\-)' | \
    $GGREP -A1 '31m\-' | \
    grep '^\^' \
    | tee "${COMMIT_DROPS_FILE}"
}

fix_history() {
    ### When the inspections are done with, we want to clean up the history
    ### Note that as part of this, we would drop "unreachable" commits that
    ### are not part of any branch's history (because these would still contain
    ### the original offending pattern.
    ###
    ### WARNING: This is the one destructive operation in this suite.
    ###
    ### You are advised to run it in a scratch full copy of your git repo.
    ###
    ### After it is successfully done, you are advised to destroy the published
    ### copy of the repo completely (e.g. on github) and force-push the cleaned
    ### one into a newly created instance of the repo, and have your team members
    ### destroy and re-fork their clones both on cloud platform and their local
    ### workspaces, so that the destroyed offending commits do not resurface.

    ### Note that you can stack more sed '-e ...' blocks below, e.g. to rewrite
    ### more patterns in one shot. Also note that the pattern and replacement
    ### representation for simple grep and regex in sed may vary... you may want
    ### to automate escaping of special chars.
    [ -n "${PATTERN_SED-}" ] || PATTERN_SED="${PATTERN}"
    git filter-branch --tree-filter "git grep '${PATTERN}' | sed 's,:.*\$,,' | sort | uniq | while read F ; do sed -e 's,${PATTERN_SED},${REPLACEMENT},g' -i '\$F'; done"
    git reflog expire --expire-unreachable=now --all
    git gc --prune=now
}

[ -n "$2" ] && PATTERN="$2"
[ -n "$3" ] && REPLACEMENT="$3"

ACTION=""
case "$1" in
    -h|--help) usage; exit 0 ;;
    find|grep) ACTION="find_commits_intro"; shift ;;
    show|diff) ACTION="find_commits_show"; shift ;;
    drop|remove|del|delete) ACTION="find_commits_drop"; shift ;;
    fix_history|find_commits_contains|find_commits_intro|find_commits_drop|find_commits_show) ACTION="$1"; shift ;;
    *) usage; exit 1 ;;
esac

echo "Running routine: '$ACTION'"
"$ACTION"